© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 95068
    Prev
    Next
    INDEX
    Explanations

    graph relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ysto
    -0.08
     }:
    -0.08
     Defined
    -0.07
    āk
    -0.07
    }:
    -0.07
    agetsi
    -0.07
     universe
    -0.07
     Isolation
    -0.07
     annum
    -0.07
    oser
    -0.07
    POSITIVE LOGITS
    _adj
    0.08
    wala
    0.07
     casc
    0.07
    ಿಕಾ
    0.07
    へ
    0.07
    inya
    0.07
    ವರು
    0.07
     구
    0.07
    (Game
    0.07
    (F
    0.07
    Activations Density 0.026%

    No Known Activations